© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117380
    Prev
    Next
    INDEX
    Explanations

    giveaway rules

    np_acts-logits-general · gemini-2.5-flash-lite

    AI assistant created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bądź
    0.57
    叅
    0.54
    ului
    0.54
     vår
    0.51
     vän
    0.51
     numai
    0.50
     მშ
    0.50
     câteva
    0.50
     complementar
    0.50
     pensar
    0.50
    POSITIVE LOGITS
    s
    0.50
    y
    0.49
    Rem
    0.47
    Accept
    0.47
    sad
    0.46
    salted
    0.45
    edict
    0.45
    胖
    0.45
    Loss
    0.45
    Released
    0.45
    Activations Density 0.001%

    No Known Activations